Real-Time Obstacle Detection in 3D Environments Using P300-based EEG Signals


Abstract views: 80 / PDF downloads: 42

Authors

  • Walid GUETTALA University of Biskra
  • Ahmed TIBERMACINE University of Biskra
  • Abdelhakim NAHILI University of Biskra
  • Imad Eddine TIBERMACINE Sapienza University of Rome
  • Abdelaziz RABEHI Djelfa University

DOI:

https://doi.org/10.59287/as-abstracts.1427

Keywords:

Obstacle Detection, P300, EEG Signals, Brain-Computer Interface, Robotics, Common Spatial Pattern, Real-Time, Human-Robot Interaction

Abstract

The research introduces a new system for obstacle detection in 3D spaces using P300 eventrelated potential from EEG signals. By incorporating brain-computer interfaces with robotics, this method enhances intuitive human-robot interaction. The system utilizes the Common Spatial Pattern (CSP) algorithm to identify distinct EEG features, improving the safety and adaptability of robots. Tested in a custom 3D simulation environment, the system demonstrated high accuracy and real-time performance, indicating its potential for applications like autonomous navigation and assistive robotics. This study represents a significant step in robotics and brain-computer interfaces, fostering a more natural user interface and propelling advancements in the field.

Author Biographies

Walid GUETTALA, University of Biskra

Department of Computer Science,Biskra. Algeria

Ahmed TIBERMACINE, University of Biskra

Department of Computer Science,  Biskra. Algeria

Abdelhakim NAHILI, University of Biskra

Department of Computer Science,  Biskra. Algeria

Imad Eddine TIBERMACINE, Sapienza University of Rome

Department of Computer, Control and Management Engineering,  Italy

Abdelaziz RABEHI, Djelfa University

Faculty of Science and Technology, Telecommunications and Smart Systems Laboratory,  Djelfa, Algeria

Downloads

Published

2023-09-02

How to Cite

GUETTALA, W., TIBERMACINE, A., NAHILI, A., TIBERMACINE, I. E., & RABEHI, A. (2023). Real-Time Obstacle Detection in 3D Environments Using P300-based EEG Signals. All Sciences Abstracts, 1(5), 8. https://doi.org/10.59287/as-abstracts.1427

Conference Proceedings Volume

Section

Articles